Merge pull request #2091 from plotly/geodataset

add a geojson dataset and link from election dataset

Author: nicolaskruchten

Diff for: packages/python/plotly/plotly/data/__init__.py

@@ -5,69 +5,100 @@
 
 def gapminder():
     """
-    Each row represents a country on a given year.
+Each row represents a country on a given year.
 
-    https://www.gapminder.org/data/
+https://www.gapminder.org/data/
 
-    Returns:
-        A `pandas.DataFrame` with 1704 rows and the following columns: `['country', 'continent', 'year', 'lifeExp', 'pop', 'gdpPercap',
-       'iso_alpha', 'iso_num']`.
-    """
+Returns:
+    A `pandas.DataFrame` with 1704 rows and the following columns:
+    `['country', 'continent', 'year', 'lifeExp', 'pop', 'gdpPercap',
+    'iso_alpha', 'iso_num']`.
+"""
     return _get_dataset("gapminder")
 
 
 def tips():
     """
-    Each row represents a restaurant bill.
+Each row represents a restaurant bill.
 
-    https://vincentarelbundock.github.io/Rdatasets/doc/reshape2/tips.html
+https://vincentarelbundock.github.io/Rdatasets/doc/reshape2/tips.html
 
-    Returns:
-        A `pandas.DataFrame` with 244 rows and the following columns: `['total_bill', 'tip', 'sex', 'smoker', 'day', 'time', 'size']`.
-    """
+Returns:
+    A `pandas.DataFrame` with 244 rows and the following columns:
+    `['total_bill', 'tip', 'sex', 'smoker', 'day', 'time', 'size']`.
+"""
     return _get_dataset("tips")
 
 
 def iris():
     """
-    Each row represents a flower.
+Each row represents a flower.
 
-    https://en.wikipedia.org/wiki/Iris_flower_data_set
+https://en.wikipedia.org/wiki/Iris_flower_data_set
 
-    Returns:
-        A `pandas.DataFrame` with 150 rows and the following columns: `['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species',
-       'species_id']`.
-    """
+Returns:
+    A `pandas.DataFrame` with 150 rows and the following columns:
+    `['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species', 'species_id']`.
+"""
     return _get_dataset("iris")
 
 
 def wind():
     """
-    Each row represents a level of wind intensity in a cardinal direction, and its frequency.
+Each row represents a level of wind intensity in a cardinal direction, and its frequency.
 
-    Returns:
-        A `pandas.DataFrame` with 128 rows and the following columns: `['direction', 'strength', 'frequency']`.
-    """
+Returns:
+    A `pandas.DataFrame` with 128 rows and the following columns:
+    `['direction', 'strength', 'frequency']`.
+"""
     return _get_dataset("wind")
 
 
 def election():
     """
-    Each row represents voting results for an electoral district in the 2013 Montreal mayoral election.
+Each row represents voting results for an electoral district in the 2013 Montreal
+mayoral election.
 
-    Returns:
-        A `pandas.DataFrame` with 58 rows and the following columns: `['district', 'Coderre', 'Bergeron', 'Joly', 'total', 'winner', 'result']`.
-    """
+Returns:
+    A `pandas.DataFrame` with 58 rows and the following columns:
+    `['district', 'Coderre', 'Bergeron', 'Joly', 'total', 'winner', 'result', 'district_id']`.
+"""
     return _get_dataset("election")
 
 
-def carshare():
+def election_geojson():
     """
-    Each row represents the availability of car-sharing services near the centroid of a zone in Montreal.
+Each feature represents an electoral district in the 2013 Montreal mayoral election.
+
+Returns:
+    A GeoJSON-formatted `dict` with 58 polygon or multi-polygon features whose `id`
+    is an electoral district numerical ID and whose `district` property is the ID and
+    district name.
+"""
+    import gzip
+    import json
+    import os
+
+    path = os.path.join(
+        os.path.dirname(os.path.dirname(__file__)),
+        "package_data",
+        "datasets",
+        "election.geojson.gz",
+    )
+    with gzip.GzipFile(path, "r") as f:
+        result = json.loads(f.read().decode("utf-8"))
+    return result
+
 
-    Returns:
-        A `pandas.DataFrame` with 249 rows and the following columns: `['centroid_lat', 'centroid_lon', 'car_hours', 'peak_hour']`.
+def carshare():
     """
+Each row represents the availability of car-sharing services near the centroid of a zone
+in Montreal.
+
+Returns:
+    A `pandas.DataFrame` with 249 rows and the following columns:
+    `['centroid_lat', 'centroid_lon', 'car_hours', 'peak_hour']`.
+"""
     return _get_dataset("carshare")